Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12459
    Prev
    Next
    INDEX
    Explanations

    references to travel and tourism, with a focus on history and culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DOCTYPE
    -0.51
     &___
    -0.51
     vois
    -0.50
    TODOS
    -0.50
     proprement
    -0.49
    Itoa
    -0.48
     насеље
    -0.46
    setImageBitmap
    -0.46
    Ơ
    -0.45
    блица
    -0.45
    POSITIVE LOGITS
     anyone
    0.71
    windowFixed
    0.69
     surla
    0.68
     Anyone
    0.61
     SwitchCompat
    0.58
    anyone
    0.57
    vician
    0.56
    TagHelper
    0.56
     anybody
    0.55
    owohl
    0.54
    Activations Density 0.137%

    No Known Activations